pathak22/context-encoder
[CVPR 2016] Unsupervised Feature Learning by Image Inpainting using GANs
Combines encoder-decoder architecture with adversarial and reconstruction losses to learn visual features through image inpainting tasks. Supports both center region and arbitrary random region inpainting modes, implemented in Torch with optional GPU acceleration and real-time visualization via display server. Pre-trained models available for Paris Street View and ImageNet datasets, with Caffe feature exports for downstream transfer learning.
905 stars. No commits in the last 6 months.
Stars
905
Forks
202
Language
Lua
License
—
Category
Last pushed
Jul 19, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/pathak22/context-encoder"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
knazeri/edge-connect
EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019...
shepnerd/inpainting_gmcnn
Image Inpainting via Generative Multi-column Convolutional Neural Networks, NeurIPS2018
youyuge34/Anime-InPainting
An application tool of edge-connect, which can do anime inpainting and drawing. 动漫人物图片自动修复，去马赛克，填补，去瑕疵
otenim/GLCIC-PyTorch
A High-Quality PyTorch Implementation of "Globally and Locally Consistent Image Completion".
kkakkkka/HunyuanPortraitLCM
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...